{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9046963453292847, "min": 1.9046963453292847, "max": 3.2957520484924316, "count": 538 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35838.765625, "min": 22702.98828125, "max": 124771.578125, "count": 538 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 73.53731343283582, "min": 42.0, "max": 999.0, "count": 538 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19708.0, "min": 11088.0, "max": 29448.0, "count": 538 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1524.2106331334362, "min": 1191.6479442202194, "max": 1541.8015807507788, "count": 477 }, "SoccerTwos.Self-play.ELO.sum": { "value": 204244.22483988045, "min": 2383.295888440439, "max": 357697.9667341807, "count": 477 }, "SoccerTwos.Step.mean": { "value": 5379912.0, "min": 9740.0, "max": 5379912.0, "count": 538 }, "SoccerTwos.Step.sum": { "value": 5379912.0, "min": 9740.0, "max": 5379912.0, "count": 538 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.017882201820611954, "min": -0.10268796980381012, "max": 0.1937672346830368, "count": 538 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.414097309112549, "min": -16.43007469177246, "max": 30.227689743041992, "count": 538 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.016559652984142303, "min": -0.11016736179590225, "max": 0.18774959444999695, "count": 538 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 2.23555326461792, "min": -17.62677764892578, "max": 29.288936614990234, "count": 538 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 538 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 538 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1477170365828055, "min": -0.6657280015945435, "max": 0.4405047601177579, "count": 538 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.94179993867874, "min": -46.371400237083435, "max": 47.535199880599976, "count": 538 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1477170365828055, "min": -0.6657280015945435, "max": 0.4405047601177579, "count": 538 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.94179993867874, "min": -46.371400237083435, "max": 47.535199880599976, "count": 538 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 538 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 538 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017182656736986247, "min": 0.010294425412818478, "max": 0.02685851512942463, "count": 256 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017182656736986247, "min": 0.010294425412818478, "max": 0.02685851512942463, "count": 256 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10605661422014237, "min": 2.5658693327083406e-07, "max": 0.1136317012210687, "count": 256 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10605661422014237, "min": 2.5658693327083406e-07, "max": 0.1136317012210687, "count": 256 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10816983431577683, "min": 2.541332889904879e-07, "max": 0.1156247744957606, "count": 256 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10816983431577683, "min": 2.541332889904879e-07, "max": 0.1156247744957606, "count": 256 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 256 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 256 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 256 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 256 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 256 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 256 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691916859", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\G:\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1691932228" }, "total": 15368.918933300001, "count": 1, "self": 4.93214799999987, "children": { "run_training.setup": { "total": 0.09903299999999993, "count": 1, "self": 0.09903299999999993 }, "TrainerController.start_learning": { "total": 15363.887752300001, "count": 1, "self": 7.99969550051901, "children": { "TrainerController._reset_env": { "total": 4.435616499999727, "count": 27, "self": 4.435616499999727 }, "TrainerController.advance": { "total": 15351.320944599482, "count": 363702, "self": 8.844116099715393, "children": { "env_step": { "total": 5833.154008899425, "count": 363702, "self": 4507.485278099248, "children": { "SubprocessEnvManager._take_step": { "total": 1320.4052337004516, "count": 363702, "self": 51.697666200741196, "children": { "TorchPolicy.evaluate": { "total": 1268.7075674997104, "count": 682466, "self": 1268.7075674997104 } } }, "workers": { "total": 5.263497099725668, "count": 363701, "self": 0.0, "children": { "worker_root": { "total": 15348.313708099879, "count": 363701, "is_parallel": true, "self": 11778.164801800305, "children": { "steps_from_proto": { "total": 0.04411069999191408, "count": 54, "is_parallel": true, "self": 0.009417199994333103, "children": { "_process_rank_one_or_two_observation": { "total": 0.03469349999758098, "count": 216, "is_parallel": true, "self": 0.03469349999758098 } } }, "UnityEnvironment.step": { "total": 3570.104795599581, "count": 363701, "is_parallel": true, "self": 180.70742649916792, "children": { "UnityEnvironment._generate_step_input": { "total": 138.96724710021127, "count": 363701, "is_parallel": true, "self": 138.96724710021127 }, "communicator.exchange": { "total": 2681.818641899953, "count": 363701, "is_parallel": true, "self": 2681.818641899953 }, "steps_from_proto": { "total": 568.6114801002484, "count": 727402, "is_parallel": true, "self": 124.4156686998341, "children": { "_process_rank_one_or_two_observation": { "total": 444.1958114004143, "count": 2909608, "is_parallel": true, "self": 444.1958114004143 } } } } } } } } } } }, "trainer_advance": { "total": 9509.322819600342, "count": 363701, "self": 59.654099500648954, "children": { "process_trajectory": { "total": 1319.1030308996862, "count": 363701, "self": 1317.5299255996854, "children": { "RLTrainer._checkpoint": { "total": 1.5731053000008615, "count": 10, "self": 1.5731053000008615 } } }, "_update_policy": { "total": 8130.565689200006, "count": 257, "self": 868.8208004000171, "children": { "TorchPOCAOptimizer.update": { "total": 7261.744888799989, "count": 7719, "self": 7261.744888799989 } } } } } } }, "trainer_threads": { "total": 1.1000010999850929e-06, "count": 1, "self": 1.1000010999850929e-06 }, "TrainerController._save_models": { "total": 0.13149460000022373, "count": 1, "self": 0.009397899999385118, "children": { "RLTrainer._checkpoint": { "total": 0.12209670000083861, "count": 1, "self": 0.12209670000083861 } } } } } } }